© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 12790
    Prev
    Next
    INDEX
    Explanations

    biocompatible, archival, Japan, Miami

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åĸĿäºĨ
    -0.21
    andr
    -0.20
    è²Ĥ
    -0.19
    éºĿ
    -0.18
    æ¯ıéļĶ
    -0.18
    åħ½
    -0.18
    æħ°
    -0.18
    uze
    -0.18
    移æ¤į
    -0.18
     ThÆ°
    -0.18
    POSITIVE LOGITS
    å¸Ĥéķ¿
    0.20
    讦
    0.19
    Keeping
    0.18
    羣æŃ£
    0.18
    Macro
    0.18
    cka
    0.18
    饱满
    0.18
    kee
    0.18
    ç¬ijç¬ij
    0.18
     pile
    0.18
    Activations Density 0.002%

    No Known Activations